Fabrizio Dini

Exploiting distinctive visual landmark maps in pan-tilt-zoom camera networks

Pan-tilt-zoom (PTZ) camera networks have an important role in surveillance systems. They have the ability to direct the attention to interesting events that occur in the scene. One method to achieve such behavior is to use a process known as sensor slaving: one (or more) master camera monitors a wide area and tracks moving targets so as to provide the positional information to one (or more) slave camera. The slave camera can thus point towards the targets in high resolution. In this paper we describe a novel framework exploiting a PTZ camera network to achieve high accuracy in the task of relating the feet position of a person in the image of the master camera, to his head position in the image of the slave camera. Each camera in the network can act as a master or slave camera, thus allowing the coverage of wide and geometrically complex areas with a relatively small number of sensors. The proposed framework does not require any 3D known location to be specified, and allows to take into account both zooming and target uncertainties. Quantitative results show good performance in target head localization, independently from the zooming factor in the slave camera. An example of cooperative tracking approach exploiting with the proposed framework is also presented.

Particle filter-based visual tracking with a first order dynamic model and uncertainty adaptation

In many real world applications, tracking must be performed reliably in real-time for sufficiently long periods where target appearance and motion may sensibly change from one frame to the following. In such non ideal conditions this is likely to determine inaccurate estimates of the target location unless dynamic components are incorporated in the model. To deal with these problems effectively, we propose a particle filter-based tracker that exploits a first order dynamic model and continuously performs adaptation of model noise so to balance uncertainty between the static and dynamic components of the state vector. We provide an extensive set of experimental evidences with a comparative performance analysis with tracking methods representative of the principal approaches. Results show that the method proposed is particularly effective for real-time tracking over long video sequences with occlusions and erratic, non-linear target motion.

Posterity Logging of Face Imagery for Video Surveillance

A real-time posterity logging system detects and tracks multiple targets in video streams, grabbing face images and retaining only the best quality for each detected target.

Adaptive uncertainty estimation for particle filter-based trackers

In particle filter-based visual trackers, dynamic velocity components are typically incorporated into the state update equations. In these cases, there is a risk that the uncertainty in the model update stage can become amplified in unexpected and undesirable ways, leading to erroneous behavior of the tracker. To deal with this problem, we propose a continuously adaptive approach to estimating uncertainty in the particle filter, one that balances the uncertainty in its static and dynamic elements. We provide quantitative performance evaluation of the resulting particle filter tracker on a set of ten video sequences. Results are reported in terms of a metric that can be used to objectively evaluate the performance of visual trackers. This metric is used to compare our modified particle filter tracker and the continuously adaptive mean shift tracker. Results show that the performance of the particle filter is significantly improved through adaptive parameter estimation, particularly in cases of occlusions and nonlinear target motion.

Improving the robustness of particle filter-based visual trackers using online parameter adaptation

In particle filter-based visual trackers, dynamic velocity components are typically incorporated into the state update equations. In these cases, there is a risk that the uncertainty in the model update stage can become amplified in unexpected and undesirable ways, leading to erroneous behavior of the tracker. Moreover, the use of a weak appearance model can make the estimates provided by the particle filter inaccurate. To deal with this problem, we propose a continuously adaptive approach to estimating uncertainty in the particle filter, one that balances the uncertainty in its static and dynamic elements. We provide quantitative performance evaluation of the resulting particle filter tracker on a set of ten video sequences. Results are reported in terms of a metric that can be used to objectively evaluate the performance of visual trackers. This metric is used to compare our modified particle filter tracker and the continuously adaptive mean shift tracker. Results show that the performance of the particle filter is significantly improved through adaptive parameter estimation, particularly in cases of occlusion and erratic, nonlinear target motion.

Uncalibrated Framework for On-line Camera Cooperation to Acquire Human Head Imagery in Wide Areas

This paper considers the problem of estimating on-line the time-variant transformation relating a persons feet position in the image of a first, fixed camera, to his head position in the image of a second, pan-tilt-zoom camera. The transformation allows to acquire high-resolution images by steering the PTZ camera at targets detected in a fixed camera view. Assuming a planar scene and modeling humans as vertical segments, we present the development of an uncalibrated framework which does not require any 3D known location to be specified, and it allows to take into account both zooming camera and target uncertainties. Results show good performances in slave camera target head localization, degrading when the high zoom factor causes a lack of feature points in the slave camera.

Pan-Tilt-Zoom Camera Networks

Abstract Pan-tilt-zoom (PTZ) camera networks play an important role in surveillance systems. They can direct attention to interesting events in the scene. One method to achieve such behavior is a process known as sensor slaving: One master camera (or more) monitors a wide area and tracks moving targets to provide positional information to one slave camera (or more). The slave camera can thus foveate at the targets in high resolution. In this chapter we consider the problem of estimating online the time-variant transformation of a humans foot position in the image of a fixed camera relative to his head position in the image of a PTZ camera. The transformation achieves high-resolution images by steering the PTZ camera at targets detected in a fixed camera view. Assuming a planar scene and modeling humans as vertical segments, we present the development of an uncalibrated framework that does not require any known 3D location to be specified and that takes into account both zooming camera and target uncertainties. Results show good performances in localizing the targets head in the slave camera view, degrading when the high zoom factor causes a lack of feature points. A cooperative tracking approach exploiting an instance of the proposed framework is presented.

Sensor Fusion for Cooperative Head Localization

In modern video surveillance systems, pan–tilt– zoom (PTZ) cameras certainly have the potential to allow the coverage of wide areas with a much smaller number of sensors, compared to the common approach of fixed camera networks. This paper describes a general framework that aims at exploiting the capabilities of modern PTZ cameras in order to acquire high resolution images of body parts, such as the head, from the observation of pedestrians moving in a wide outdoor area. The framework allows to organize the sensors in a network with arbitrary topology, and to establish pairwise master–slave relationship between them. In this way a slave camera can be steered to acquire imagery of a target keeping into account both target and zooming uncertainties. Experiments show good performance in localizing target’s head, independently from the zooming factor of the slave camera.

Natural Human–Computer Interaction

Research work in relation to Natural Human–Computer Interaction concerns the theorization and development of systems that understand and recognize human communicative actions in order to engage people in a dialogue between them and their surroundings.